A Self-Improving Architecture for Dynamic Safety in Large Language Models
Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to autonomously detect safety failures and synthesize defense policies at runtime, without retraining or manual intervention. Method: We propose the Self-Improving Safety Framework (SISF), grounded in the MAPE-K reference model. The framework couples a target LLM with a feedback loop: an Adjudicator detects breaches, a Policy Synthesis Module generates dual-mechanism defense policies (heuristic and semantic), and a Warden enforces them. We conducted seven experiments (10,061 evaluations) across four model families. Results: Across five reproducibility trials, SISF achieved a mean Attack Success Rate (ASR) of 0.27% (+/-0.15%), autonomously generating 240 policies per trial. Cross-model evaluation confirmed deployment portability. A held-out test showed a 68.5% proactive interception rate on unseen attacks. Stacked behind Llama Guard 4, the combined defense reduced residual ASR from 7.88% to 0.00%. Ablation confirmed both heuristic and semantic policy types are architecturally required. Conclusion: Self-adaptive architecture is a viable approach to LLM safety. SISF achieves sub-1% ASR through synchronous output monitoring, progressively shifting enforcement to fast, local Warden policies via the MAPE-K loop, offering a new pattern for building resilient AI systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models
Large vision-language models (LVLMs) are vulnerable to harmful input compared to their language-only backbones. We investigated this vulnerability by exploring LVLMs internal dynamics, framing their inherent safety under…
When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models
Aligned vision-language models (VLMs) are designed to balance grounded visual reasoning with safe generation behavior. However, we observe a striking phenomenon: under safety-constrained instruction, models frequently ab…
Visual ReasoningCan Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models
Safety alignment is critical for deploying large language models (LLMs) in real-world applications, yet most existing approaches rely on large human-annotated datasets and static red-teaming benchmarks that are costly, d…
MetaSC: Test-Time Safety Specification Optimization for Language Models
We propose a novel dynamic safety framework that optimizes language model (LM) safety reasoning at inference time without modifying model weights. Building on recent advances in self-critique methods, our approach levera…
Language ModelingLanguage ModellingAgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of…